Damage detection of a cable-stayed bridge using feature extraction and selection methods

Bisheh, Hossein Babajanian; Amiri, Gholamreza Ghodrati; Nekooei, Masoud; Darvishan, Ehsan

doi:10.1080/15732479.2019.1599964

Cited by 40 publications

(5 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The diagnosis of a structural system using ultrasonic-based methods can be reformed as a pattern recognition problem that constitutes three essential steps: (a) feature extraction, (b) feature selection, and (c) damage classification. Recently, the artificial NN (ANN) and support vector machine (SVM) are the widely used pattern recognition algorithm for the diagnosis of structural and mechanical systems [26][27][28]. However, these methods have three inherent shortcomings.…”

Section: Introductionmentioning

confidence: 99%

A deep learning approach for anomaly identification in PZT sensors using point contact method

Kalimullah

Shelke

Habib

2023

Smart Mater. Struct.

View full text Add to dashboard Cite

The implementation of piezoelectric sensors is degraded due to surface defects, delamination, and extreme weathering conditions, to mention a few. The sensor needs to be diagnosed before the efficacious implementation in the structural health monitoring (SHM) framework. A novel experimental method based on Coulomb coupling is utilised to visualise the evolution of elastic waves and interaction with the surface anomaly in the Lead Zirconate Titanate (PZT) substrate. Machine learning is expeditiously becoming an essential technology for scientific computing, with several possibilities to advance the field of structural health monitoring (SHM). This study employs a deep learning-based autoencoder neural network in conjunction with image registration and PSNR to diagnose the surface anomaly in the PZT substrate. The autoencoder extracts the significant damage-sensitive features from the complex waveform big data. The autoencoder provides a non-linear input-output model that is well suited for the non-linear interaction of the wave with the surface anomaly and boundary of the substrate. The mean absolute error (MAE) in the reconstruction of the sequential signal from the autoencoder network is evaluated. The MAEs are sensitive to the anomaly that lies in the PZT substrate. Image registration is leveraged to overcome the challenge due to the offset in the data. Further, the localisation and quantification of the anomaly are performed by computing PSNR values. This work proposes an advanced, efficient damage detection algorithm in the scenario of big data that is ubiquitous in SHM.

show abstract

Section: Introductionmentioning

confidence: 99%

A deep learning approach for anomaly identification in PZT sensors using point contact method

Kalimullah

Shelke

Habib

2023

Smart Mater. Struct.

View full text Add to dashboard Cite

show abstract

“…These ML-SHM techniques, which utilize structural vibration response as the primary data type, have four stages: health definition, data acquisition, feature engineering, and machine-learned damage assessment. Arguments for the damage prediction power of ML have been made in several studies [4][5][6][7]. These studies have focused on addressing feature engineering through extracting and selecting features that result in more effective ML model training.…”

Section: Introduction 456mentioning

confidence: 99%

Data-Driven Approach for Assessment of Seismic Damage in Wood Buildings

Muin

Iqbal

Lindt

2023

World Conference on Timber Engineering (WCTE 2023)

View full text Add to dashboard Cite

Advances in modern computing techniques and capabilities have been utilized in development of new structural health monitoring techniques that utilize a significant volume of data from instrumentation. These data-driven methods open new possibilities for the damage assessment of wood (or any) buildings. A method known as feature engineering is a key step in developing such tools. This paper presents a feature engineering procedure for wood buildings based on data recorded during seismic events and utilizes a full-scale wood shake table test data set and damage inspection results to illustrate the procedure.

show abstract

“…These features are computed in the time domain and provide a summary of the statistics of the signal over the feature extraction window. Some of the primary statistical time domain features used include mean, variance, standard deviation, skewness, kurtosis, Root Mean Square (RMS) [26][27][28] and the difference in empirical cumulative distribution functions. 29 Statistical features such as RMS have also been used in combination with modal parameters as Damage Sensitive Features (DSFs).…”

Section: Introductionmentioning

confidence: 99%

“…68 A number of filter, wrapper and embedded feature selection approaches have been applied to the binary scenario where two data sets are available from the Tianjin Yonghe Bridge before and after a damage occurrence. 27,47,69 . Feature selection based on a genetic algorithm (GA) is proposed in Ref.…”

Section: Introductionmentioning

confidence: 99%

A Feature Extraction & Selection Benchmark for Structural Health Monitoring

Buckley

Ghosh

Pakrashi

2022

Structural Health Monitoring

View full text Add to dashboard Cite

There are a large number of time domain, frequency domain and time-frequency signal processing methods available for univariate feature extraction. However, there is no consensus in SHM on which feature, or feature sets, are best suited for the identification, localisation and prognosis of damage. This paper attempts to address this problem by providing a comprehensive benchmark of feature selection & reduction methods applied to an extensive set of univariate features. These univariate features are extracted using multiple statistical, temporal and spectral methods from the benchmark S101 and Z24 bridge datasets. These datasets contain labelled accelerometer recordings from full scale bridges as they are progressively subjected to multiple damage scenarios. To identify the minimal set of features that best distinguishes between the multiple damage states, a supervised machine learning approach is used in combination with multiple feature selection methods. The ability of these reduced feature sets to distinguish between damage states is benchmarked using the prediction performance of the classification models, with the training and test sets obtained through stratified k-fold cross validation. The results obtained show that reduced sets of univariate features, extracted from a single accelerometer sensor, are capable of accurately distinguishing between multiple classes of healthy and damaged states. This work provides a benchmark for SHM practitioners and researchers alike for the choice, comparison and validation of feature extraction and feature selection methods across a wide range of systems.

show abstract

Damage detection of a cable-stayed bridge using feature extraction and selection methods

Cited by 40 publications

References 33 publications

A deep learning approach for anomaly identification in PZT sensors using point contact method

A deep learning approach for anomaly identification in PZT sensors using point contact method

Data-Driven Approach for Assessment of Seismic Damage in Wood Buildings

A Feature Extraction & Selection Benchmark for Structural Health Monitoring

Contact Info

Product

Resources

About